# CassandraSemanticCache > **Class** in `langchain_community` 📖 [View in docs](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache) Cache that uses Cassandra as a vector-store backend for semantic (i.e. similarity-based) lookup. Example: .. code-block:: python import cassio from langchain_community.cache import CassandraSemanticCache from langchain_core.globals import set_llm_cache cassio.init(auto=True) # Requires env. variables, see CassIO docs my_embedding = ... set_llm_cache(CassandraSemanticCache( embedding=my_embedding, table_name="my_semantic_cache", )) It uses a single (vector) Cassandra table and stores, in principle, cached values from several LLMs, so the LLM's llm_string is part of the rows' primary keys. One can choose a similarity measure (default: "dot" for dot-product). Choosing another one ("cos", "l2") almost certainly requires threshold tuning. (which may be in order nevertheless, even if sticking to "dot"). ## Signature ```python CassandraSemanticCache( self, session: Optional[CassandraSession] = None, keyspace: Optional[str] = None, embedding: Optional[Embeddings] = None, table_name: str = CASSANDRA_SEMANTIC_CACHE_DEFAULT_TABLE_NAME, distance_metric: Optional[str] = None, score_threshold: float = CASSANDRA_SEMANTIC_CACHE_DEFAULT_SCORE_THRESHOLD, ttl_seconds: Optional[int] = CASSANDRA_SEMANTIC_CACHE_DEFAULT_TTL_SECONDS, skip_provisioning: bool = False, similarity_measure: str = CASSANDRA_SEMANTIC_CACHE_DEFAULT_DISTANCE_METRIC, setup_mode: CassandraSetupMode = CassandraSetupMode.SYNC, ) ``` ## Description **Note:** The session and keyspace parameters, when left out (or passed as None), fall back to the globally-available cassio settings if any are available. In other words, if a previously-run 'cassio.init(...)' has been executed previously anywhere in the code, Cassandra-based objects need not specify the connection parameters at all. ## Parameters | Name | Type | Required | Description | |------|------|----------|-------------| | `session` | `Optional[CassandraSession]` | No | an open Cassandra session. Leave unspecified to use the global cassio init (see below) (default: `None`) | | `keyspace` | `Optional[str]` | No | the keyspace to use for storing the cache. Leave unspecified to use the global cassio init (see below) (default: `None`) | | `embedding` | `Optional[Embeddings]` | No | Embedding provider for semantic encoding and search. (default: `None`) | | `table_name` | `str` | No | name of the Cassandra (vector) table to use as cache. There is a default for "simple" usage, but remember to explicitly specify different tables if several embedding models coexist in your app (they cannot share one cache table). (default: `CASSANDRA_SEMANTIC_CACHE_DEFAULT_TABLE_NAME`) | | `distance_metric` | `Optional[str]` | No | an alias for the 'similarity_measure' parameter (see below). As the "distance" terminology is misleading, please prefer 'similarity_measure' for clarity. (default: `None`) | | `score_threshold` | `float` | No | numeric value to use as cutoff for the similarity searches (default: `CASSANDRA_SEMANTIC_CACHE_DEFAULT_SCORE_THRESHOLD`) | | `ttl_seconds` | `Optional[int]` | No | time-to-live for cache entries (default: None, i.e. forever) (default: `CASSANDRA_SEMANTIC_CACHE_DEFAULT_TTL_SECONDS`) | | `similarity_measure` | `str` | No | which measure to adopt for similarity searches. Note: this parameter is aliased by 'distance_metric' - however, it is suggested to use the "similarity" terminology since this value is in fact a similarity (i.e. higher means closer). Note that at most one of the two parameters 'distance_metric' and 'similarity_measure' can be provided. (default: `CASSANDRA_SEMANTIC_CACHE_DEFAULT_DISTANCE_METRIC`) | | `setup_mode` | `CassandraSetupMode` | No | a value in langchain_community.utilities.cassandra.SetupMode. Choose between SYNC, ASYNC and OFF - the latter if the Cassandra table is guaranteed to exist already, for a faster initialization. (default: `CassandraSetupMode.SYNC`) | ## Extends - `BaseCache` ## Constructors ```python __init__( self, session: Optional[CassandraSession] = None, keyspace: Optional[str] = None, embedding: Optional[Embeddings] = None, table_name: str = CASSANDRA_SEMANTIC_CACHE_DEFAULT_TABLE_NAME, distance_metric: Optional[str] = None, score_threshold: float = CASSANDRA_SEMANTIC_CACHE_DEFAULT_SCORE_THRESHOLD, ttl_seconds: Optional[int] = CASSANDRA_SEMANTIC_CACHE_DEFAULT_TTL_SECONDS, skip_provisioning: bool = False, similarity_measure: str = CASSANDRA_SEMANTIC_CACHE_DEFAULT_DISTANCE_METRIC, setup_mode: CassandraSetupMode = CassandraSetupMode.SYNC, ) ``` | Name | Type | |------|------| | `session` | `Optional[CassandraSession]` | | `keyspace` | `Optional[str]` | | `embedding` | `Optional[Embeddings]` | | `table_name` | `str` | | `distance_metric` | `Optional[str]` | | `score_threshold` | `float` | | `ttl_seconds` | `Optional[int]` | | `skip_provisioning` | `bool` | | `similarity_measure` | `str` | | `setup_mode` | `CassandraSetupMode` | ## Properties - `session` - `keyspace` - `embedding` - `table_name` - `similarity_measure` - `score_threshold` - `ttl_seconds` - `table` ## Methods - [`update()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/update) - [`aupdate()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/aupdate) - [`lookup()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/lookup) - [`alookup()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/alookup) - [`lookup_with_id()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/lookup_with_id) - [`alookup_with_id()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/alookup_with_id) - [`lookup_with_id_through_llm()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/lookup_with_id_through_llm) - [`alookup_with_id_through_llm()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/alookup_with_id_through_llm) - [`delete_by_document_id()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/delete_by_document_id) - [`adelete_by_document_id()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/adelete_by_document_id) - [`clear()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/clear) - [`aclear()`](https://reference.langchain.com/python/langchain-community/cache/CassandraSemanticCache/aclear) --- [View source on GitHub](https://github.com/langchain-ai/langchain-community/blob/4b280287bd55b99b44db2dd849f02d66c89534d5/libs/community/langchain_community/cache.py#L1209)